Image Generation Script with PicLumen and Botasaurus

Introduction

For bulk image generation—crucial for mass publishing—you need efficient automation. This image generation script uses PicLumen, a free tool, and the Botasaurus library in Python to create images from text queries listed in a file. We’ll walk through the setup and code step-by-step.

Setup

Create a project folder and set up a virtual environment:

py -m venv .venv
.venv\Scripts\activate

Install dependencies:

pip install python-dotenv botasaurus requests pillow pyperclip

Create queries.txt with image prompts, one per line (e.g., “sunset over mountains”). Then, add a .env file with your PicLumen credentials after registering:

LOGIN=your_email
PASSWORD=your_password

The Script (main.py)

Here’s the optimized Botasaurus image generator script for PicLumen scraping:

from botasaurus.browser import browser, Driver, Wait
import os
import time
from dotenv import load_dotenv
import requests
from io import BytesIO
from PIL import Image

# Load environment variables
load_dotenv()
login = os.getenv("LOGIN")
password = os.getenv("PASSWORD")

# Global settings
global_image_counter = 0
num_images_to_download = 4  # Limit per query

# Paths
base_dir = os.path.dirname(__file__)
images_dir = os.path.join(base_dir, 'images')
os.makedirs(images_dir, exist_ok=True)

# URLs and headers
login_url = 'https://piclumen.com/app/account'
dashboard_url = 'https://piclumen.com/app/image-generator/create'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/85.0.4183.121'
}

def read_queries_from_file(file_path):
    """Read text queries from a file."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            return [line.strip() for line in f if line.strip()]
    except FileNotFoundError:
        print(f"Error: {file_path} not found.")
        return []

def process_image_links(driver, images_dir):
    """Extract image URLs from the page."""
    images = driver.select_all('img[src^="https://cdn.piclumen.com"]', wait=Wait.LONG)
    return [img.get_attribute('src') for img in images if img.get_attribute('src')]

@browser(
    reuse_driver=True,  # Reuse browser instance
    wait_for_complete_page_load=False,
    headless=True  # Optional: run without UI
)
def piclumen(driver: Driver, data=None):
    global global_image_counter
    
    # Login
    driver.get(login_url, wait=5)
    driver.type('input[placeholder="Email"]', login, wait=1)
    driver.type('input[placeholder="Password"]', password, wait=1)
    driver.click('#app > div > div.content > div.absolute > div.w-full > div > div.w-80 > div > div.mt-8 > button', wait=5)
    driver.get(dashboard_url, wait=10)

    # Open settings once
    driver.click('.tool-bar-item', wait=3)  # Adjust selector if needed
    
    # Load queries
    queries = read_queries_from_file(os.path.join(base_dir, 'queries.txt'))
    print(f"Processing {len(queries)} queries")

    for query in queries:
        print(f"Generating images for: {query}")
        try:
            # Set to generate 4 images
            driver.click('#confExtendArea > div > div.flex.gap-4 > div:nth-child(3) > div > div:nth-child(4)', wait=3)

            # Input query
            driver.type('textarea', query, wait=2)
            driver.click('#confExtendArea > div > div.mt-3 > div > div.flex.gap-3 > button > span', wait=3)
            
            # Wait for generation (adjust time based on observation)
            time.sleep(80)

            # Extract and download images
            image_urls = process_image_links(driver, images_dir)
            for url in image_urls[:num_images_to_download]:
                try:
                    response = requests.get(url, headers=headers)
                    response.raise_for_status()
                    img = Image.open(BytesIO(response.content))
                    global_image_counter += 1
                    output_path = os.path.join(images_dir, f"image_{global_image_counter}.png")
                    img.save(output_path, 'PNG')
                    print(f"Saved: {output_path}")
                except Exception as e:
                    print(f"Error saving {url}: {e}")
        except Exception as e:
            print(f"Error processing '{query}': {e}")

if __name__ == "__main__":
    piclumen()

How it works:

• Logs into PicLumen with credentials from .env.
• Reads queries from queries.txt.
• Generates 4 images per query, downloads them as PNGs.
• Saves images with a global counter in the images folder.

Conclusion

This image generation script leverages PicLumen’s free service and Botasaurus for a cost-effective Python image automation solution. Perfect for bulk content creation in 2025, it simplifies generating images from text queries. Adjust the wait time or image count as needed, and enjoy free, automated image production!